{"id":"W2159136633","doi":"10.5555/2627435.2750354","title":"Efficient learning and planning with compressed predictive states","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005894953,0.0001819664,0.000341643,0.0006333191,0.0006205583,0.0004457496,0.0007378692,0.00006792065,0.00001393811],"category_scores_gemma":[0.002185107,0.0001332722,0.00005125783,0.0005861575,0.0002047649,0.00022323,0.0004703248,0.003118607,0.000009896463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000080681,"about_ca_system_score_gemma":0.0001076706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000222164,"about_ca_topic_score_gemma":4.209511e-7,"domain_scores_codex":[0.9957034,0.001343142,0.0004425854,0.0002948857,0.001645549,0.000570457],"domain_scores_gemma":[0.9959605,0.00223669,0.0004558372,0.0002106442,0.0008819324,0.0002544201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001315104,0.00002716824,0.05697921,0.0000376587,0.0000519098,0.00005595272,0.002530865,0.9361988,0.000260343,0.0004711334,0.00006811733,0.003187376],"study_design_scores_gemma":[0.001011535,0.002984463,0.007667805,0.0002789267,0.00000966031,0.0001517915,0.0004611005,0.9808924,0.0001317663,0.00008085598,0.006186198,0.0001434924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893721,0.0003850899,0.8081517,0.0004733903,0.00008708872,0.000105579,1.394694e-7,0.00006202696,0.00136288],"genre_scores_gemma":[0.9846391,0.00005298628,0.01452557,0.00002490605,0.0001487018,0.000002234473,0.000001510804,0.00002565146,0.0005793448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.795267,"threshold_uncertainty_score":0.9991812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249183959460578,"score_gpt":0.331304983517485,"score_spread":0.3063865875714272,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}